project coordinator: prof. pedro j. sanz website: ... · the project the objectives · cooperative...
TRANSCRIPT
THE PROJECT
THE OBJECTIVES
· Cooperative navigation techniques to achieve robust, high
accuracy navigation (localization) of all the vehicles involved
in the robotic team.
· Innovative mapping algorithms to robustly build consistent
multimodal maps of the seafloor.
· Guidance and control algorithms for the team vehicles alone
but also to cooperatively guide and control both vehicles in
formation.
· Embedded knowledge representation framework and the
highlevel reasoning agents required.
· Advanced acoustic/optical image processing algorithms to
allow for feature detection and tracking.
· A redundant robotic arm endowed with a dexterous hand as
an enabling technology for multipurpose manipulation
underwater.
· Innovative strategies for the coordinated control of the joint
AUV-Manipulator system.
· The mechatronics as well as the perception/action
capabilities needed to face the autonomous docking of the I-
AUV to the ASC.
· A multisensory control architecture, including a knowledge-
based approach, to guarantee the suitable manipulation
actions for enabling a multipurpose intervention system.
THE RESULTS
UWSim, an UnderWater SIMulator for marine robotics research and development, which has been used as a tool for testing and integrat ing percept ion and con t ro l a l gor i thms before runn i ng t hem on t he r ea l robots . More i n fo : h t tp : / /www.irs.uji.es/uwsim/
The different pars of the I-AUV were tested in the CIRS water tank: navigation, vision and manipulation. Furthermore, the I-AUV performed an autonomous search and recover mission of a flight data recorder mockup, placed at an unknown position into the water tank.
In the harbour experiments (Oct. 2011), the I-AUV performed both survey and intervention phases autonomously. When the target was found in the image, the vehicle switched to visual station keeping and the manipulation started. The procedure is as fo l low ing : 1 ) the image i s p rocessed and the t a rge t identified and tracked, 2) the grasping module decides the best position for the I-AUV, 3) the I-AUV adopts the requested pose, 4) the task is performed. T r a c k i n g i s p e r f o r m e d continuously while the grasping takes place.
Project coordinator: Prof. Pedro J. SanzWebsite: www.irs.uji.es/trident
Email: [email protected]: /trident-project
Twitter: @IRSlab @ViCOROB
PHASE I (Survey):1) Launching.2) Survey.3) Recovery.
Target selection& interventionspecification
PHASE II(Intervention):4) Launching.5) Approaching.6) Intervention.7) Recovery.
The Consortium
EU FP-7, ICT Challenge 2: Cognitive Systems, Interaction, Robotics Collaborative Project (STREP).Grant agreement No: ICT-248497
This project proposes a new methodology to p r o v i d e m u l t i p u r p o s e d e x t e r o u s manipulation capabilities for intervention operations in unknown, unstructured and underwater environments.